KNOULEDGE ACQLISITIO\ FOR A\ I\TER\ \L REVELLE SERk ICE CLASSIFICATIO\ SYSTEbI

This paper introduces the Automated Issue Identification System (MS), an expert system prototype designed and built in a joint effort between the Internal Revenue Service and Bolt Beranek and Newman Inc. The intent of the paper is to identify the steps taken toward a successful artificial intelligence approach to a government application. The paper will describe the classification task as currently performed by IRS auditors, and the e.xpected benefits of automating this task with an expert system. The multi-year project schedule will be outlined, with the first year objectives of the knowledge engineering team more specifically detailed. Knowledge engineering techniques and procedures used in the initial phases of the project will be examined, including the advantages and challenges of working with several experts. The main phases of the know-ledge engineering process will be described, from the initial task analysis, through early modeling of the IRS experts by the system, to the very effective rapid prototyping cycle supported by the object-oriented programming environment used in this project. This paper concludes with the current status of the prototype and the knowledge acquisition process, and a discussion of future goals.